© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31001
    Prev
    Next
    INDEX
    Explanations

    for x, y, N

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĢİ
    -0.09
     TL
    -0.09
    ti
    -0.09
    _ANY
    -0.08
    erb
    -0.08
     (~
    -0.08
    fang
    -0.08
    rou
    -0.08
     Arnold
    -0.08
     wol
    -0.08
    POSITIVE LOGITS
     blah
    0.34
     XYZ
    0.33
     xyz
    0.31
    XYZ
    0.25
     bla
    0.24
     X
    0.24
    blah
    0.23
     xxx
    0.22
     xxxx
    0.22
     XXX
    0.22
    Activations Density 0.526%

    No Known Activations